© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85461
    Prev
    Next
    INDEX
    Explanations

    of what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    textAlignment
    -1.46
     falleció
    -1.43
     murió
    -1.37
    alnya
    -1.35
     pertanian
    -1.34
     padx
    -1.33
     delante
    -1.32
     וגם
    -1.32
    еме
    -1.31
    時間も
    -1.30
    POSITIVE LOGITS
     of
    2.38
     what
    2.17
     how
    1.80
     who
    1.80
     —
    1.77
     whom
    1.75
     why
    1.70
     که
    1.45
     things
    1.37
     sorts
    1.31
    Activations Density 0.153%

    No Known Activations